Beidouqixing/minimax-h3-4step-lora-flashgen
214.7k
MiniMax-H3 4-Step LoRA (FlashGen)
4-step distilled LoRA for MiniMax-H3 text-to-video+audio (T2VA). Trained on Ascend NPU with data-free distillation; merge into the base model and inject base_schedule before vllm-omni / MindIE-SD deployment.
Files
Training config
Usage
Requires base model MiniMaxAI/MiniMax-H3.
Merge with merge_lora_ckpt.py before vllm-omni / MindIE deployment:
python merge_lora_ckpt.py \
${MODEL_ROOT}/FL2VA \
minimax_h3_4step_lora_flashgen_v1.0_768p_bf16.safetensors \
./minimax-h3-4step-flashgen
export MODEL=./minimax-h3-4step-flashgen/FL2VADeployment (MindIE-SD / vllm-omni)
For Ascend NPU inference and serving, see the MindIE-SD deployment guide:
- MiniMax-H3 推理部署文档(含 4 步蒸馏权重合并与启动)
- MindIE-SD 仓库:Ascend/MindIE-SD
